Incorporating literature knowledge in Bayesian network for inferring gene networks with gene expression data

Authors:
Eyad Almasri;Peter Larsen;Guanrao Chen;Yang Dai
Affiliations:
University of Illinois at Chicago, Chicago, IL;University of Illinois at Chicago, Chicago, IL;University of Illinois at Chicago, Chicago, IL;University of Illinois at Chicago, Chicago, IL
Venue:
ISBRA'08 Proceedings of the 4th international conference on Bioinformatics research and applications
Year:
2008

Citing 5
Cited 1

A Bayesian Method for the Induction of Probabilistic Networks from Data

Machine Learning
Priors on network structures. Biasing the search for Bayesian networks

Priors on network structures. Biasing the search for Bayesian networks
Probabilistic discovery of overlapping cellular processes and their regulation

RECOMB '04 Proceedings of the eighth annual international conference on Resaerch in computational molecular biology
A new dynamic Bayesian network (DBN) approach for identifying gene regulatory networks from time course microarray data

Bioinformatics
On the sample complexity of learning Bayesian networks

UAI'96 Proceedings of the Twelfth international conference on Uncertainty in artificial intelligence

Using Gene Expression Modeling to Determine Biological Relevance of Putative Regulatory Networks

ISBRA '09 Proceedings of the 5th International Symposium on Bioinformatics Research and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

The reconstruction of gene networks from microarray geneexpression has been a challenging problem in bioinformatics. Variousmethods have been proposed for this problem. The incorporation of variousgenomic and proteomic data has been shown to enhance the learningability in the Bayesian Network (BN) approach. However, the knowledgeembedded in the large body of published literature has not been utilizedin a systematic way. In this work, prior knowledge on gene interactionwas derived based on the statistical analysis of published interactionsbetween pairs of genes or gene products. This information was used (1)to construct a structure prior and (2) to reduce the search space in theBN algorithm. The performance of the two approaches was evaluatedand compared with the BN method without prior knowledge on twotime course microarray gene expression data related to the yeast cell cycle.The results indicate that the proposed algorithms can identify edgesin learned networks with higher biological relevance. Furthermore, themethod using literature knowledge for the reduction of the search spaceoutperformed the method using a structure prior in the BN framework.